© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10734
    Prev
    Next
    INDEX
    Explanations

    byby affectedby influenceby followed by effectby or unaffected by

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects the phrase "affected by" which appears in scientific texts describing how one variable influences another.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects numeric measurement values (including decimals and percentages) in scientific contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    пы
    -1.45
    спект
    -1.44
    <>());
    -1.44
    –
    -1.44
    Ljava
    -1.43
    Ѕ
    -1.43
     []:
    -1.38
    </h4>
    -1.38
    l
    -1.38
    л
    -1.33
    POSITIVE LOGITS
     it
    1.73
     you
    1.64
     übri
    1.50
     licencias
    1.48
     colecciones
    1.41
     været
    1.40
     pasaron
    1.39
     wyboru
    1.38
     veicolo
    1.37
     faldas
    1.36
    Activations Density 0.099%

    No Known Activations